Gustavo De Veciana

Full Professor, University of Texas, Austin

1 paper at NeurIPS 2025

Homepage· OpenReview· Semantic Scholar· Google Scholar

Poster Session 2

1 paper

Wednesday, December 3, 2025 · 4:30 PM → 7:30 PM

Exhibit Hall C,D,E

Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks

#115 Spotlight · Heasung Kim, Taekyun Lee, Hyeji Kim, Gustavo De Veciana

A novel risk-averse training framework that leverages score-based generative models for data augmentation tailored to Conditional Value-at-Risk minimization